Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
184 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
45 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Supervised Auto-Encoding Twin-Bottleneck Hashing (2306.11122v1)

Published 19 Jun 2023 in cs.LG

Abstract: Deep hashing has shown to be a complexity-efficient solution for the Approximate Nearest Neighbor search problem in high dimensional space. Many methods usually build the loss function from pairwise or triplet data points to capture the local similarity structure. Other existing methods construct the similarity graph and consider all points simultaneously. Auto-encoding Twin-bottleneck Hashing is one such method that dynamically builds the graph. Specifically, each input data is encoded into a binary code and a continuous variable, or the so-called twin bottlenecks. The similarity graph is then computed from these binary codes, which get updated consistently during the training. In this work, we generalize the original model into a supervised deep hashing network by incorporating the label information. In addition, we examine the differences of codes structure between these two networks and consider the class imbalance problem especially in multi-labeled datasets. Experiments on three datasets yield statistically significant improvement against the original model. Results are also comparable and competitive to other supervised methods.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (42)
  1. Tensorflow: A system for large-scale machine learning. In 12th {normal-{\{{USENIX}normal-}\}} symposium on operating systems design and implementation ({normal-{\{{OSDI}normal-}\}} 16), pages 265–283, 2016.
  2. Hashing with binary matrix pursuit. In Proceedings of the European conference on computer vision (ECCV), pages 332–348, 2018.
  3. Mlsmote: Approaching imbalanced multilabel learning through synthetic instance generation. Knowledge-Based Systems, 89:385–397, 2015.
  4. del jesus, and francisco herrera. 2015.“addressing imbalance in multilabel classification: Measures and random resampling algorithms.”. Neurocomputing. https://doi. org/10.1016/j. neucom, 91, 2014.
  5. Smote: synthetic minority over-sampling technique. Journal of artificial intelligence research, 16:321–357, 2002.
  6. Efficient classification of multi-label and imbalanced data using min-max modular classifiers. In The 2006 IEEE International Joint Conference on Neural Network Proceedings, pages 1770–1775. IEEE, 2006.
  7. Nus-wide: a real-world web image database from national university of singapore. In Proceedings of the ACM international conference on image and video retrieval, pages 1–9, 2009.
  8. Learning to hash with binary deep neural network. In European Conference on Computer Vision, pages 219–234. Springer, 2016.
  9. Smote for learning from imbalanced data: progress and challenges, marking the 15-year anniversary. Journal of artificial intelligence research, 61:863–905, 2018.
  10. Managing imbalanced data sets in multi-label problems: a case study with the smote algorithm. In Iberoamerican Congress on Pattern Recognition, pages 334–342. Springer, 2013.
  11. Iterative quantization: A procrustean approach to learning binary codes for large-scale image retrieval. IEEE transactions on pattern analysis and machine intelligence, 35(12):2916–2929, 2012.
  12. Imbalanced multi-modal multi-label learning for subcellular localization prediction of human proteins with both single and multiple sites. PloS one, 7(6):e37155, 2012.
  13. 3d object recognition based on canonical angles between shape subspaces. In Asian Conference on Computer Vision, pages 580–591. Springer, 2010.
  14. Product quantization for nearest neighbor search. IEEE transactions on pattern analysis and machine intelligence, 33(1):117–128, 2010.
  15. Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907, 2016.
  16. Bartosz Krawczyk. Learning from imbalanced data: open challenges and future directions. Progress in Artificial Intelligence, 5(4):221–232, 2016.
  17. Learning multiple layers of features from tiny images. 2009.
  18. Improvement of learning algorithm for the multi-instance multi-label rbf neural networks trained with imbalanced samples. J. Inf. Sci. Eng., 29(4):765–776, 2013.
  19. Deep supervised discrete hashing. arXiv preprint arXiv:1705.10999, 2017.
  20. Feature learning based deep supervised hashing with pairwise labels. arXiv preprint arXiv:1511.03855, 2015.
  21. Microsoft coco: Common objects in context. In European conference on computer vision, pages 740–755. Springer, 2014.
  22. Deep supervised hashing for fast image retrieval. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 2064–2072, 2016.
  23. Supervised hashing with kernels. In 2012 IEEE Conference on Computer Vision and Pattern Recognition, pages 2074–2081. IEEE, 2012.
  24. Umap: Uniform manifold approximation and projection for dimension reduction. arXiv preprint arXiv:1802.03426, 2018.
  25. Deep reinforcement learning for image hashing. IEEE Transactions on Multimedia, 22(8):2061–2073, 2019.
  26. Auto-encoding twin-bottleneck hashing. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 2818–2827, 2020.
  27. Le Song. Stochastic generative hashing. In ICML, 2017.
  28. Rethinking the inception architecture for computer vision. CoRR, abs/1512.00567, 2015.
  29. Multilabel classification using heterogeneous ensemble of multi-label classifiers. Pattern Recognition Letters, 33(5):513–523, 2012.
  30. Inverse random under sampling for class imbalance problem and its application to multi-label classification. Pattern Recognition, 45(10):3738–3750, 2012.
  31. Multi-label imbalanced data enrichment process in neural net classifier training. In 2008 IEEE International Joint Conference on Neural Networks (IEEE World Congress on Computational Intelligence), pages 1301–1307. IEEE, 2008.
  32. Wasserstein auto-encoders. arXiv preprint arXiv: 1711.01558, 2017.
  33. Laurens Van der Maaten and Geoffrey Hinton. Visualizing data using t-sne. Journal of machine learning research, 9(11), 2008.
  34. Learning hash codes with listwise supervision. In Proceedings of the IEEE International Conference on Computer Vision, pages 3032–3039, 2013.
  35. A survey on learning to hash. IEEE transactions on pattern analysis and machine intelligence, 40(4):769–790, 2017.
  36. Deep supervised hashing with triplet labels. In Asian conference on computer vision, pages 70–84. Springer, 2016.
  37. Deep reinforcement learning with label embedding reward for supervised image hashing. arXiv preprint arXiv:2008.03973, 2020.
  38. Spectral hashing. In Nips, volume 1, page 4. Citeseer, 2008.
  39. Supervised hashing for image retrieval via image representation learning. In Proceedings of the AAAI conference on artificial intelligence, volume 28, 2014.
  40. Relaxation-free deep hashing via policy gradient. In Proceedings of the European Conference on Computer Vision (ECCV), pages 134–150, 2018.
  41. Composite quantization for approximate nearest neighbor search. In International Conference on Machine Learning, pages 838–846. PMLR, 2014.
  42. Deep hashing network for efficient similarity retrieval. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 30, 2016.

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now